trainer_state.json

{
  "best_metric": 0.9245333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0599/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 43.6282958984375,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.4993,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.4340735971927643,
      "eval_runtime": 13.5491,
      "eval_samples_per_second": 276.772,
      "eval_steps_per_second": 4.355,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 35.062191009521484,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.3236,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9005333333333333,
      "eval_loss": 0.33885690569877625,
      "eval_runtime": 13.2607,
      "eval_samples_per_second": 282.791,
      "eval_steps_per_second": 4.449,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 44.03160858154297,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.1458,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9189333333333334,
      "eval_loss": 0.3053337335586548,
      "eval_runtime": 13.4296,
      "eval_samples_per_second": 279.235,
      "eval_steps_per_second": 4.393,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.38559913635254,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.0717,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.29896828532218933,
      "eval_runtime": 13.3319,
      "eval_samples_per_second": 281.28,
      "eval_steps_per_second": 4.425,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 61.62545394897461,
      "learning_rate": 0.0,
      "loss": 0.034,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9245333333333333,
      "eval_loss": 0.27657073736190796,
      "eval_runtime": 13.2143,
      "eval_samples_per_second": 283.783,
      "eval_steps_per_second": 4.465,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}